Benchmark Almanac

Mementos

GPT-4V 40.6%
Not in model cards

Models describe what happens across a sequence of images. The evaluation checks whether their descriptions capture the objects and actions.

Made by
Xiyao Wang and colleagues
Released
January 2024
Kind
General visual questions
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Images, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
Last model added
November 2023
Scores refreshed
November 20th, 2026
9
Entries in its paper, 1 model we track

GPT-4V leads with 40.6% GPT-4V leads with 40.6%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the plain mean of object and behavior F1 across three domains, in percent. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

  1. 1 GPT-4V Sequential 40.6%
  2. 2 Gemini Sequential 32.7%
  3. 3 LLaVa-1.5 Combined 27.6%
  4. 4 Chat-UniVi Sequential 26.3%
  5. 5 mPLUG_Owl-v2 Combined 23.6%
  6. 6 InstructBLIP Combined 22.1%
  7. 7 Video-LLaMA-2 Sequential 16.1%
  8. 8 MiniGPT5 Combined 14.4%
  9. 9 MiniGPT4 Combined 14.1%

Source: The Mementos paper

Source: The Mementos paper

#EntryScoreSettingDateSource
1 GPT-4V 40.6% Sequential Nov 2023 Official leaderboard
2 Gemini 32.7% Sequential Official leaderboard
3 LLaVa-1.5 27.6% Combined Official leaderboard
4 Chat-UniVi 26.3% Sequential Official leaderboard
5 mPLUG_Owl-v2 23.6% Combined Official leaderboard
6 InstructBLIP 22.1% Combined Official leaderboard
7 Video-LLaMA-2 16.1% Sequential Official leaderboard
8 MiniGPT5 14.4% Combined Official leaderboard
9 MiniGPT4 14.1% Combined Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4V 40.6% Sequential Nov 2023 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-4V 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-4V

Source: Official Mementos leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in November 2023, for GPT-4V. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 1 model we track, plus 8 other entries on its leaderboard.
  • Warning Newest score The newest came 3 years ago, in November 2023, for GPT-4V.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 40.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 2 rows for models we track and 8 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check